Method, device and readable storage medium for determining potential off-grid users

Abstract

The application discloses a method and device for determining potential off-grid users and a readable storage medium, relates to the technical field of communication, and is used for accurately determining potential off-grid users. The method comprises the following steps: acquiring a measurement report of a user in a target cell in a historical time period; the measurement report comprises measurement results of multiple types of measurement indexes; for a first type of measurement index, determining a candidate off-grid probability score corresponding to the measurement result of the first type of measurement index and a weight; the first type is any one of the multiple types; performing weighted processing on the multiple candidate off-grid probability scores according to the weight of each type of measurement index to obtain an off-grid probability score of the user; and in the case that the off-grid probability score is greater than a first threshold, determining that the user is a potential off-grid user.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of communication, and in particular, to a method and device for determining potential off-network users and a readable storage medium. BACKGROUND

[0002] At present, after more than ten years of market expansion, the user scale growth of the communication market is slowing down, and the market competition is also tending to saturation. When planning a network, an operator usually adopts the following methods: 1. Based on user income, the network problems of areas with high user income are solved first; 2. Based on user terminals, the network problems of areas with high user terminal aggregation are solved first; 3. Based on user business, the network problems of areas with high user traffic are solved first; 4. Based on user perception, the network problems of areas with poor user perception are solved first.

[0003] However, when planning a network, the operator does not consider the factor that users may change operators due to poor network of the operator, resulting in a large number of potential off-network users. When the potential off-network users off-network, it will affect the income of the operator. SUMMARY

[0004] The present application provides a method and device for determining potential off-network users and a readable storage medium, which are used to accurately determine potential off-network users.

[0005] To achieve the above purpose, the present application adopts the following technical solutions:

[0006] In a first aspect, a method for determining potential off-network users is provided, comprising: obtaining a measurement report of a user in a target cell in a historical time period; the measurement report comprising measurement results of multiple types of measurement indexes; determining, for a first type of measurement index, a candidate off-network probability score corresponding to the measurement result of the first type of measurement index and a weight; the first type being any one of the multiple types; performing weighted processing on the multiple candidate off-network probability scores according to the weight of each type of measurement index to obtain an off-network probability score of the user; and determining the user as a potential off-network user if the off-network probability score is greater than a first threshold.

[0007] Based on the technical solutions provided in the present application, the determining apparatus obtains the measurement report of the user in the target cell in a historical time period; the measurement report includes measurement results of multiple types of measurement indexes; for a first type of measurement index, the determining apparatus determines the candidate off-network probability score and the weight corresponding to the measurement result of the first type of measurement index; the first type is any one of the multiple types. In this way, since the types of the measurement results of the multiple types of measurement indexes are different, the determining apparatus can determine the user experience from multiple angles. Further, the determining apparatus performs weighted processing on the multiple candidate off-network probability scores according to the weight of each type of measurement index to obtain the off-network probability score of the user; in the case where the off-network probability score is greater than a first threshold, the user is determined to be a potential off-network user. In this way, based on the measurement results of the multiple types of measurement indexes, the user experience can be considered from all aspects and quantitatively processed, and whether the user is a potential off-network user can be more accurately determined.

[0008] Optionally, the multiple types of measurement indexes include a first measurement index, a second measurement index, and a third measurement index; the first measurement index includes multiple first sub-measurement indexes, and the multiple first sub-measurement indexes include received power RSRP, channel quality indicator CQI, downlink sensing rate, and uplink and downlink physical resource block PRB utilization rate; the second measurement index includes multiple second sub-measurement indexes, and the multiple second sub-measurement indexes include round-trip time RTT and hypertext transfer protocol HTTP response success rate; and the third measurement index includes multiple third sub-measurement indexes, and the multiple third sub-measurement indexes include the number of times of VOLTE voice unconnected and the number of times of VOLTE call drop.

[0009] Optionally, the alternative off-network probability score of the first measurement index comprises: determining index scores and weights of a plurality of first sub-measurement indexes; wherein the index score of RSRP is 0 when the sampling proportion of the measurement result of RSRP greater than or equal to the second threshold value is less than the third threshold value, and the index score of RSRP is 1 when the sampling proportion of the measurement result of RSRP less than the second threshold value is greater than or equal to the third threshold value; the index score of CQI is 0 when the sampling proportion of the measurement result of CQI greater than or equal to the fourth threshold value is less than the fifth threshold value, and the index score of CQI is 1 when the sampling proportion of the measurement result of CQI greater than or equal to the fourth threshold value is greater than or equal to the fifth threshold value; the index score of downlink perception rate is 0 when the measurement result of downlink perception rate is less than the sixth threshold value, and the index score of downlink perception rate is 1 when the measurement result of downlink perception rate is greater than or equal to the sixth threshold value; the index score of PRB utilization rate is 0 when the measurement result of PRB utilization rate is greater than the seventh threshold value, and the index score of PRB utilization rate is 1 when the measurement result of PRB utilization rate is less than or equal to the seventh threshold value; and the index scores of the plurality of first sub-measurement indexes are weighted to obtain the alternative off-network probability score of the first measurement index according to the weights of the plurality of first sub-measurement indexes.

[0010] Optionally, the alternative off-network probability score of the second measurement index comprises: determining index scores and weights of a plurality of second sub-measurement indexes; the index score of RTT delay is 0 when the number of times that the measurement result of RTT delay is greater than the eighth threshold value is greater than the ninth threshold value, and the index score of RTT delay is 1 when the number of times that the measurement result of RTT delay is greater than the eighth threshold value is less than or equal to the ninth threshold value; the index score of HTTP response success rate is 0 when the HTTP response success rate is less than the tenth threshold value; the index score of HTTP response success rate is 1 when the HTTP response success rate is greater than or equal to the tenth threshold value; and the index scores of the plurality of second sub-measurement indexes are weighted to obtain the alternative off-network probability score of the second measurement index according to the weights of the plurality of second sub-measurement indexes.

[0011] Optionally, the determining the candidate off-network probability score of the third measurement index comprises: determining index scores and weights of a plurality of third sub-measurement indexes; in a case that the measurement result of the number of VOLTE voice call failures is greater than the number threshold, the index score of the number of VOLTE voice call failures is 0, and in a case that the measurement result of the number of VOLTE voice call failures is less than or equal to the number threshold, the index score of the number of VOLTE voice call failures is 1; in a case that the measurement result of the number of VOLTE call drops is greater than the number threshold, the index score of the number of VOLTE call drops is 0, and in a case that the measurement result of the number of VOLTE call drops is less than or equal to the number threshold, the index score of the number of VOLTE call drops is 1; and performing weighted processing on the index scores of the plurality of third sub-measurement indexes according to the weights of the plurality of third sub-measurement indexes to obtain the candidate off-network probability score of the third measurement index.

[0012] In a second aspect, a device for determining a potential off-network user is provided. The device comprises: an obtaining unit, a determining unit, and a processing unit. The obtaining unit is configured to obtain a measurement report of a user in a target cell in a historical time period. The measurement report comprises measurement results of a plurality of types of measurement indexes. The determining unit is configured to determine, for a first type of measurement index, a candidate off-network probability score corresponding to the measurement result of the first type of measurement index and a weight. The first type is any one of the plurality of types. The processing unit is configured to perform weighted processing on a plurality of candidate off-network probability scores according to the weight of each type of measurement index to obtain an off-network probability score of the user. The determining unit is further configured to determine the user as a potential off-network user in a case that the off-network probability score is greater than a first threshold.

[0013] Optionally, the plurality of types of measurement indexes comprise a first measurement index, a second measurement index, and a third measurement index. The first measurement index comprises a plurality of first sub-measurement indexes, and the plurality of first sub-measurement indexes comprise received signal power (RSRP), channel quality indicator (CQI), downlink perceived rate, and uplink and downlink physical resource block (PRB) utilization rate. The second measurement index comprises a plurality of second sub-measurement indexes, and the plurality of second sub-measurement indexes comprise round-trip time (RTT) and hypertext transfer protocol (HTTP) response success rate. The third measurement index comprises a plurality of third sub-measurement indexes, and the plurality of third sub-measurement indexes comprise the number of long term evolution voice bearer (VOLTE) voice call failures and the number of VOLTE call drops.

[0014] Optionally, the determining unit is specifically configured to: determine the index score and the weight of the plurality of first sub-measurement indexes; wherein the index score of the RSRP is 0 in a case that the sampling proportion of the measurement result of the RSRP being greater than or equal to the second threshold value is less than the third threshold value, and the index score of the RSRP is 1 in a case that the sampling proportion of the measurement result of the RSRP being less than the second threshold value is greater than or equal to the third threshold value; the index score of the CQI is 0 in a case that the sampling proportion of the measurement result of the CQI being greater than or equal to the fourth threshold value is less than the fifth threshold value, and the index score of the CQI is 1 in a case that the sampling proportion of the measurement result of the CQI being greater than or equal to the fourth threshold value is greater than or equal to the fifth threshold value; the index score of the downlink perception rate is 0 in a case that the measurement result of the downlink perception rate is less than the sixth threshold value, and the index score of the downlink perception rate is 1 in a case that the measurement result of the downlink perception rate is greater than or equal to the sixth threshold value; the index score of the PRB utilization rate is 0 in a case that the measurement result of the PRB utilization rate is greater than the seventh threshold value, and the index score of the PRB utilization rate is 1 in a case that the measurement result of the PRB utilization rate is less than or equal to the seventh threshold value; and the index scores of the plurality of first sub-measurement indexes are weighted to obtain the candidate off-network probability score of the first measurement index according to the weight of the plurality of first sub-measurement indexes.

[0015] Optionally, the determining unit is specifically further configured to: determine the index score and the weight of the plurality of second sub-measurement indexes; the index score of the RTT delay is 0 in a case that the number of times that the measurement result of the RTT delay is greater than the eighth threshold value is greater than the ninth threshold value, and the index score of the RTT delay is 1 in a case that the number of times that the measurement result of the RTT delay is greater than the eighth threshold value is less than or equal to the ninth threshold value; the index score of the HTTP response success rate is 0 in a case that the HTTP response success rate is less than the tenth threshold value; the index score of the HTTP response success rate is 1 in a case that the HTTP response success rate is greater than or equal to the tenth threshold value; and the index scores of the plurality of second sub-measurement indexes are weighted to obtain the candidate off-network probability score of the second measurement index according to the weight of the plurality of second sub-measurement indexes.

[0016] Optionally, the determining unit is further configured to: determine the index score and the weight of each of the third sub-measurement indexes; in a case where the measurement result of the VOLTE voice call drop times is greater than the threshold, the index score of the VOLTE voice call drop times is 0, and in a case where the measurement result of the VOLTE voice call drop times is less than or equal to the threshold, the index score of the VOLTE voice call drop times is 1; and perform weighted processing on the index scores of the third sub-measurement indexes according to the weights of the third sub-measurement indexes to obtain the candidate off-network probability score of the third measurement index.

[0017] In a third aspect, a potential off-network user determining apparatus is provided, which can implement the functions of the potential off-network user determining apparatus in the above aspects or possible designs. For example, in one possible design, the potential off-network user determining apparatus can include a processor and a communication interface, and the processor can be configured to support the potential off-network user determining apparatus to implement the functions involved in the first aspect or any of the possible designs of the first aspect.

[0018] In another possible design, the potential off-network user determining apparatus can further include a memory configured to store computer-executable instructions and data necessary for the potential off-network user determining apparatus. When the potential off-network user determining apparatus is running, the processor executes the computer-executable instructions stored in the memory, so that the potential off-network user determining apparatus performs the potential off-network user determining method in the first aspect or any of the possible designs of the first aspect.

[0019] In a fourth aspect, a computer-readable storage medium is provided, which can be a readable nonvolatile storage medium, and the computer-readable storage medium stores computer instructions or programs. When the computer instructions or programs are run on a computer, the computer can perform the potential off-network user determining method in the first aspect or any of the possible designs of the first aspect.

[0020] In a fifth aspect, a computer program product including instructions is provided. When the computer program product is run on a computer, the computer can perform the potential off-network user determining method in the first aspect or any of the possible designs of the first aspect.

[0021] In a sixth aspect, an electronic device is provided, which includes one or more processors and one or more memories. The one or more memories are coupled to the one or more processors, and the one or more memories are configured to store computer program codes comprising computer instructions. When the one or more processors execute the computer instructions, the electronic device is caused to perform the method for determining a potential off-network user as described in the first aspect or any possible design of the first aspect.

[0022] In a seventh aspect, a chip system is provided, which includes a processor and a communication interface. The chip system can be used to implement the functions performed by the apparatus for determining a potential off-network user as described in the first aspect or any possible design of the first aspect. In a possible design, the chip system further includes a memory configured to store program instructions and / or data. The chip system can be constituted by a chip, or can include a chip and other discrete devices, without limitation. BRIEF DESCRIPTION OF DRAWINGS

[0023] Figure 1 A schematic diagram of a system for determining a potential off-network user according to an embodiment of the present application;

[0024] Figure 2 A structural schematic diagram of an apparatus for determining a potential off-network user according to an embodiment of the present application;

[0025] Figure 3 A flowchart of a method for determining a potential off-network user according to an embodiment of the present application;

[0026] Figure 4 A flowchart of another method for determining a potential off-network user according to an embodiment of the present application;

[0027] Figure 5 A flowchart of another method for determining a potential off-network user according to an embodiment of the present application;

[0028] Figure 6 A flowchart of another method for determining a potential off-network user according to an embodiment of the present application;

[0029] Figure 7 A structural schematic diagram of another apparatus for determining a potential off-network user according to an embodiment of the present application. DETAILED DESCRIPTION

[0030] In order to make the ordinary person skilled in the art better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings.

[0031] It should be noted that the terms "first", "second", and the like in the description and in the claims of the present application and the above-described accompanying drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the disclosure described herein can be implemented in an order other than that illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of the present application as detailed in the appended claims.

[0032] It should also be understood that the term "comprising" indicates the presence of the described features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, and / or components.

[0033] At present, after more than ten years of market expansion, the user size growth is slowing down, and the market competition is also tending to saturation. When planning the network, the operators usually plan the network in the following ways: 1. Based on user income, the network problems in areas with high user income are solved first; 2. Based on user terminals, the network problems in areas with user terminal aggregation are solved first; 3. Based on user business, the network problems in areas with high user traffic are solved first; 4. Based on user perception, the network problems in areas with poor user perception are solved first.

[0034] However, when planning the network, the operators do not consider the factor that users may change operators due to poor operator network, resulting in a large number of potential off-network users. When the potential off-network users off-network, it will affect the income of the operator.

[0035] In view of this, the embodiments of the present application provide a method for determining potential off-network users, comprising: acquiring a measurement report of a user in a target cell in a historical time period; the measurement report comprising measurement results of multiple types of measurement indicators; for a first type of measurement indicator, determining a candidate off-network probability score and a weight corresponding to the measurement result of the first type of measurement indicator; the first type being any one of the multiple types; weighting the multiple candidate off-network probability scores according to the weight of each type of measurement indicator to obtain an off-network probability score of the user; and determining the user as a potential off-network user if the off-network probability score is greater than a first threshold.

[0036] The method provided by the embodiments of the present application will be described in detail below with reference to the accompanying drawings of the specification.

[0037] It should be noted that the network system described in the embodiments of the present application is for more clearly illustrating the technical solutions of the embodiments of the present application, and does not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those skilled in the art can know that, with the evolution of network systems and the appearance of other network systems, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0038] Figure 1 A schematic diagram of a potential off-network user determination system provided by an embodiment of the present application is shown. As shown in the figure, the potential off-network user determination system can include a network device 11 and a potential off-network user determination apparatus 12. The network device 11 is connected to the potential off-network user determination apparatus 12 (hereinafter referred to as determination apparatus 12). For example, the network device 11 and the determination apparatus 12 can be connected by a wireless manner, or can be connected by a wired manner, and the embodiments of the present application do not make a limitation in this regard. Figure 1

[0039] In the embodiments of the present application, the network device 11 can be a base station, an operator database, a data processing center, a server, etc. The embodiments of the present application do not make a limitation on the specific technology, the specific number and the specific device form of the network device 11.

[0040] In the embodiments of the present application, the determination apparatus 12 can be a server, a computer, etc., and can also be referred to as a terminal, a mobile station (MS), a mobile terminal (MT), etc. It is a device that provides voice and / or data connectivity to users, for example, the determination apparatus 12 can be a handheld device with wireless connection function, a vehicle-mounted device, etc. Specifically, it can be a mobile phone, a pocket personal computer (PPC), a palm computer, a personal digital assistant (PDA), a notebook computer, a tablet computer, a wearable device, or a vehicle-mounted device, etc. The embodiments of the present application do not make a limitation on the specific technology, the specific number and the specific device form of the determination apparatus 12. The embodiments of the present application do not make a limitation on the specific technology, the specific number and the specific device form of the determination apparatus 12.

[0041] ​The network device 11 measures the user's target cell, generates a measurement report of the user within a historical time period of the target cell, and sends the measurement report to the determining device 12. The determining device 12, upon receiving the measurement report from the network device 11, determines the candidate churn probability score and weight corresponding to the measurement results of the first type of measurement indicator, and weights the multiple candidate churn probability scores according to the weight of each type of measurement indicator to obtain the user's churn probability score. Further, it determines whether the user is a potential churner based on the churn probability score.

[0042] In different application scenarios, network device 11 and determining device 12 can be independent devices or integrated into the same device. This embodiment of the invention does not impose specific limitations on this.

[0043] It should be noted that, Figure 1 This is just an example framework diagram. Figure 1 The names of the various devices included are unrestricted, and except for Figure 1 In addition to the functional nodes shown, other nodes may also be included, but this application embodiment does not limit this.

[0044] In practical implementation, Figure 1 Each device in the process can be adopted Figure 2 The shown composition structure, or including Figure 2 The components shown. Figure 2 This is a schematic diagram illustrating the composition of a determining device 200 provided in an embodiment of this application. The determining device 200 can be a server, or it can be a chip or system-on-a-chip within the server. Figure 2 As shown, the determining device 200 includes a processor 201, a communication interface 202, and a communication line 203.

[0045] Furthermore, the determining device 200 may also include a memory 204. The processor 201, memory 204, and communication interface 202 can be connected via a communication line 203.

[0046] The processor 201 can be a CPU, a general-purpose processor, a network processor (NP), a digital signal processor (DSP), a microprocessor, a microcontroller, a programmable logic device (PLD), or any combination thereof. The processor 201 can also be other devices with processing capabilities, such as circuits, devices, or software modules, without limitation.

[0047] Communication interface 202 is used to communicate with other devices or other communication networks. Communication interface 202 can be a module, circuit, communication interface, or any device capable of enabling communication.

[0048] Communication line 203 is used to transmit information between the components included in determining device 200.

[0049] Memory 204 is used to store instructions. These instructions can be computer programs.

[0050] The memory 204 can be a read-only memory (ROM) or other type of static storage device that can store static information and / or instructions; it can also be a random access memory (RAM) or other type of dynamic storage device that can store information and / or instructions; it can also be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, etc., without limitation.

[0051] It should be noted that the memory 204 can exist independently of the processor 201 or can be integrated with the processor 201. The memory 204 can be used to store instructions, program code, or some data, etc. The memory 204 can be located inside or outside the determining device 200, without limitation. The processor 201 is used to execute the instructions stored in the memory 204 to implement the method for determining potential offline users provided in the following embodiments of this application.

[0052] In one example, processor 201 may include one or more CPUs, for example, Figure 2 CPU0 and CPU1 in the CPU.

[0053] As an optional implementation, the determining device 200 includes multiple processors, for example, besides Figure 2 In addition to processor 201, it may also include processor 205.

[0054] It should be pointed out that, Figure 2 The composition shown does not constitute a basis for the interpretation of this invention. Figure 1 The limitations of each device in the process, except Figure 2 In addition to the components shown, Figure 1 The various devices in the can include ratio Figure 2More or fewer components, or combinations of certain components, or different arrangements of components.

[0055] In this embodiment of the application, the chip system may be composed of chips or may include chips and other discrete devices.

[0056] Furthermore, the actions, terms, etc., involved in the various embodiments of this application can be referenced interchangeably without limitation. The message names or parameter names in the messages exchanged between the various devices in the embodiments of this application are merely examples, and other names may be used in specific implementations without limitation.

[0057] To facilitate a clear description of the technical solutions in the embodiments of this application, the terms "first" and "second" are used in the embodiments of this application to distinguish identical or similar items with essentially the same function and effect. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order, and the terms "first" and "second" are not necessarily different.

[0058] It should be noted that, in this application, the terms "exemplary" or "for example" are used to indicate that something is being described as an example, illustration, or illustration. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or design solutions. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0059] In this application, "at least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0060] The following is combined Figure 1 The system for determining potential churned users shown herein describes the method for determining potential churned users provided in the embodiments of this application.

[0061] Figure 3 This application provides a method for determining potential offline users, which can be applied to a server or a determining device. Figure 1The determining device 12 can also be a component within the determining device 12, such as a chip. This application embodiment uses an application to the determining device 12 as an example for illustration. Figure 4 As shown, the method includes the following steps S301-S304:

[0062] S301. Determine if the device acquires measurement reports of the target cell where the user is located within a historical time period.

[0063] The measurement report includes measurement results for various types of metrics. The user can be any user within a specific operator or a user meeting preset criteria. For example, it could be a user with monthly spending exceeding a preset value, or a 4G or 5G user. The target cell can be the user's primary cell or a neighboring cell. The historical time period can be set as needed. For example, it could be the day before the current time or the hour before the current time.

[0064] The measurement metrics include multiple types: a first measurement metric, a second measurement metric, and a third measurement metric. The first measurement metric comprises several first sub-measurements, including reference signal receiving power (RSRP), channel quality indicator (CQI), downlink sensing rate, and uplink / downlink physical resource block (PRB) utilization. The second measurement metric comprises several second sub-measurements, including round-trip time (RTT) and Hypertext Transfer Protocol (HTTP) response success rate. The third measurement metric comprises several third sub-measurements, including the number of failed voice calls on Voice over Long-Term Evolution (VoLTE) and the number of dropped VoLTE calls.

[0065] As one possible implementation, the determining device can communicate with a network device. The determining device can send a first subscription message to the network device, requesting measurement reports from the user within a historical time period of the target cell. Upon receiving the first subscription message from the determining device, the network device can determine the user's measurement reports within the historical time period of the target cell from the signaling plane of a unified deep packet inspection (DPI) system. The unified DPI system converts each segment of control information into an external data representation (XDR) and sends a first reply message to the determining device, which includes the user's measurement reports within the historical time period of the target cell. After receiving the first reply message from the network device, the determining device can obtain the user's measurement reports within the historical time period of the target cell based on the first reply message.

[0066] It should be noted that the possible implementations of this step are merely illustrative examples and are not intended to be limiting.

[0067] S302. The determining device determines the candidate off-grid probability score and weight corresponding to the measurement result of the measurement index of the first type for the first type of measurement index.

[0068] The first type can be any one of several types. The weight corresponding to the measurement result of the first type of measurement indicator can be set as needed. For example, it can be 1 / 3, etc.

[0069] As one possible implementation, the determining device can determine the candidate off-grid probability score corresponding to the measurement result of the first type of measurement index based on the index scores and weights of multiple sub-measurement indices corresponding to the first type of measurement index.

[0070] It should be noted that the specific details of the possible implementation methods for this step can be found in the descriptions of the subsequent steps, and will not be repeated here.

[0071] S303. The determining device performs weighted processing on the multiple candidate churn probability scores according to the weight of each type of measurement index to obtain the user's churn probability score.

[0072] In one possible implementation, the device is equipped with a calculation unit. The calculation unit can perform a weighted summation of the complaint rates of multiple types of goods based on the weight of each type of complaint rate to obtain the complaint index of the target merchant account.

[0073] For example, the determination device can weight multiple alternative churn probability scores according to the following formula to obtain the user's churn probability score.

[0074] Formula 4: P = w1*p1 + w2*p2 + w3*p3

[0075] Where P represents the user's churn probability score. p1 represents the candidate churn probability score for the first measurement indicator. p2 represents the candidate churn probability score for the second measurement indicator. p3 represents the candidate churn probability score for the third measurement indicator. w1 represents the weight corresponding to the first measurement indicator. w2 represents the weight corresponding to the second measurement indicator. w3 represents the weight corresponding to the third measurement indicator.

[0076] S304. If the churn probability score is greater than the first threshold, the device determines that the user is a potential churn user.

[0077] The first threshold can be set as needed. For example, it can be 0.5, 0.6, or 0.9, etc.

[0078] As one possible implementation, the determining device includes a comparator that compares the churn probability score with a first threshold. The determining device can then determine whether the churn probability score exceeds the first threshold. Furthermore, if the churn probability score exceeds the first threshold continuously, the determining device identifies the user as a potential churner.

[0079] It should be noted that the higher the churn probability score, the greater the user's churn probability.

[0080] Based on the technical solution provided in this application, the device determines the measurement report of the user within a historical time period in the target cell. The measurement report includes measurement results of multiple types of measurement indicators. For a first type of measurement indicator, the device determines the candidate churn probability score and weight corresponding to the measurement result of the first type of measurement indicator. The first type can be any one of multiple types. Thus, since the measurement results of multiple measurement indicators are of different types, the device can determine the user experience from multiple perspectives. Furthermore, the device weights the multiple candidate churn probability scores according to the weight of each type of measurement indicator to obtain the user's churn probability score. If the churn probability score is greater than a first threshold, the user is determined to be a potential churn user. Therefore, based on the measurement results of multiple measurement indicators, the user experience can be comprehensively considered and quantified, more accurately determining whether a user is a potential churn user.

[0081] One possible implementation, such as Figure 4 As shown, in order to determine the candidate off-grid probability score of the first measurement index, the determination method of this application may further include S401-S402 as described below.

[0082] S401, The determining device determines the index scores and weights of multiple first sub-measurement indicators.

[0083] The weights of multiple first sub-measurements can be set as needed. For example, they can be 1 / 4.

[0084] As one possible implementation, after acquiring the user's measurement report for the target cell within a historical time period, the determining device can determine the measurement results of the target cell's RSRP, Channel Quality Indicator (CQI), Downlink Sensing Rate, and Uplink / Downlink Physical Resource Block (PRB) utilization from the measurement report. Based on the measurement results of the target cell's RSRP, CQI, downlink sensing rate, and PRB utilization, it determines the score of multiple first sub-measurement indicators. Specifically, this may include:

[0085] The determination device assigns an RSRP score of 0 when the sampling percentage of RSRP measurements greater than or equal to the second threshold is less than the third threshold, and an RSRP score of 1 when the sampling percentage of RSRP measurements less than the second threshold is greater than or equal to the third threshold. Similarly, the determination device assigns a CQI score of 0 when the sampling percentage of CQI measurements greater than or equal to the fourth threshold is less than the fifth threshold, and an CQI score of 1 when the sampling percentage of CQI measurements greater than or equal to the fourth threshold is greater than or equal to the fifth threshold.

[0086] If the measured downlink sensing rate is less than the sixth threshold, the downlink sensing rate index score is determined to be 0; if the measured downlink sensing rate is greater than or equal to the sixth threshold, the downlink sensing rate index score is determined to be 1.

[0087] If the measured PRB utilization rate is greater than the seventh threshold, the PRB utilization rate index score is determined to be 0; if the measured PRB utilization rate is less than or equal to the seventh threshold, the PRB utilization rate index score is determined to be 1.

[0088] It should be noted that PRB utilization rate can be either uplink PRB utilization rate or downlink PRB utilization rate.

[0089] It should be noted that the second, third, fourth, fifth, sixth, and seventh thresholds can be set as needed. For example, the second threshold can be -112 dBm. The third threshold can be 90%. The fourth threshold can be 7%. The fifth threshold can be 80%. The sixth threshold can be 5 Mbps. The seventh threshold can be 70%.

[0090] S402. The determining device performs weighted processing on the index scores of multiple first sub-measurement indices according to their weights, and obtains the candidate off-grid probability score of the first measurement index.

[0091] It should be noted that the weighted processing procedure can be referred to the specific description in S303 above, and will not be repeated here.

[0092] In this way, the determining device can determine the index scores and weights of multiple first sub-measurement indicators based on the measurement reports of the target cell where the user is located within a historical time period.

[0093] One possible implementation, such as Figure 5 As shown, in order to determine the candidate off-grid probability score of the second measurement index, the determination method of this application may further include the following S501-S502.

[0094] S501, The determining device determines the index scores and weights of multiple second sub-measurement indicators.

[0095] The weights of multiple second sub-measures can be set as needed. For example, they can be 1 / 2.

[0096] As one possible implementation, after acquiring measurement reports of users in the target cell within a historical time period, the determining device can extract measurement results for the target cell's RTT latency and HTTP response success rate from these reports. Based on these measurement results, it then determines scores for multiple second sub-measurement metrics. Specifically, this may include:

[0097] If the number of times the measured RTT delay exceeds the eighth threshold is greater than the ninth threshold, the downlink sensing rate score is determined to be 0; if the number of times the measured RTT delay exceeds the eighth threshold is less than or equal to the ninth threshold, the RTT delay score is determined to be 1.

[0098] The device determines that if the HTTP response success rate is less than the ninth threshold, the HTTP response success rate metric score is 0; if the HTTP response success rate is greater than or equal to the ninth threshold, the HTTP response success rate metric score is 1.

[0099] It should be noted that RTT latency can include uplink RTT latency and downlink RTT latency.

[0100] It should be noted that the eighth, ninth, and tenth thresholds can be set as needed. For example, the eighth threshold can be 300 millimeters (ms), the ninth threshold can be 14, and the tenth threshold can be 80%.

[0101] S502. The determining device performs weighted processing on the index scores of multiple second sub-measurement indicators according to the weights of multiple second sub-measurement indicators, and obtains the candidate off-grid probability score of the second measurement indicator.

[0102] It should be noted that the weighted processing procedure can be referred to the specific description in S303 above, and will not be repeated here.

[0103] In this way, the determining device can determine the index scores and weights of multiple second sub-measurement indicators based on the measurement reports of the target cell where the user is located within a historical time period.

[0104] One possible implementation, such as Figure 6 As shown, in order to obtain a well-trained traffic prediction model, the determination method of this application may further include the following steps S601-S602.

[0105] S601, The determining device determines the index scores and weights of multiple third sub-measurement indicators.

[0106] The weights of multiple third-level sub-measures can be set as needed. For example, they can be 1 / 2.

[0107] As one possible implementation, after acquiring the user's measurement report for the target cell within a historical time period, the determining device can identify the number of VoLTE voice call failures and VoLTE call drops within the target cell from the measurement report. Based on the measurement results of the number of VoLTE voice call failures and VoLTE call drops in the target cell, it can determine the scores of multiple third sub-measurement indicators. Specifically, these may include:

[0108] If the measured number of VoLTE voice call failures exceeds the threshold, the device determines the score for the VoLTE voice call failure count as 0; if the measured number of VoLTE voice call failures is less than or equal to the threshold, the device determines the score for the VoLTE voice call failure count as 1.

[0109] If the measured number of VoLTE dropped calls is greater than the threshold, the device determines the score of the VoLTE dropped call count as 0; if the measured number of VoLTE dropped calls is less than or equal to the threshold, the device determines the score of the VoLTE dropped call count as 1.

[0110] It should be noted that the number of VoLTE voice calls that were not connected can include the number of VoLTE outgoing voice calls that were not connected or the number of VoLTE incoming voice calls that were not connected.

[0111] It should be noted that the number of attempts threshold can be set as needed. For example, the number of attempts threshold can be 1, 2, etc.

[0112] S602. The determining device performs weighted processing on the index scores of multiple third sub-measurement indicators according to the weights of multiple third sub-measurement indicators, and obtains the candidate off-grid probability score of the third measurement indicator.

[0113] It should be noted that the weighted processing procedure can be referred to the specific description in S303 above, and will not be repeated here.

[0114] In this way, the determining device can determine the index scores and weights of multiple third sub-measurement indicators based on the measurement reports of the target cell where the user is located within a historical time period.

[0115] The various solutions in the above embodiments of this application can be combined without contradiction.

[0116] This application embodiment can divide the determining device into functional modules or functional units according to the above method examples. For example, each function can be divided into a separate functional module or functional unit, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or in software functional modules or functional units. The module or unit division in this application embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0117] When dividing each function into modules according to its corresponding function. Figure 7 A schematic diagram of a determining device is shown. This determining device can be a server or a chip applied in a server. This determining device can be used to perform the functions related to the server involved in the above embodiments. Figure 7 The determining device shown may include: an acquisition unit 701, a determining unit 702, and a processing unit 703; the acquisition unit 701 is used to acquire the user's measurement report within a historical time period in the target cell; the measurement report includes measurement results of multiple types of measurement indicators; the determining unit 702 is used to determine the candidate churn probability score and weight corresponding to the measurement results of the first type of measurement indicator; the first type can be any one of multiple types; the processing unit 703 is used to perform weighted processing on the multiple candidate churn probability scores according to the weight of each type of measurement indicator to obtain the user's churn probability score; the determining unit 702 is also used to determine the user as a potential churn user if the churn probability score is greater than a first threshold.

[0118] In one possible design, multiple types of measurement metrics include a first measurement metric, a second measurement metric, and a third measurement metric. The first measurement metric includes multiple first sub-measurement metrics, such as Received Power (RSRP), Channel Quality Indicator (CQI), Downlink Sensing Rate, and Uplink / Downlink Physical Resource Block (PRB) utilization. The second measurement metric includes multiple second sub-measurement metrics, such as Round-Trip Time (RTT) and Hypertext Transfer Protocol (HTTP) response success rate. The third measurement metric includes multiple third sub-measurement metrics, such as the number of VoLTE (Voice over LTE) call failures and the number of VoLTE call drops.

[0119] In one possible design, the determining unit 702 is specifically used for: determining the candidate churn probability score of the first measurement index, including: determining the index scores and weights of multiple first sub-measurement indices; wherein, if the sampling proportion where the RSRP measurement result is greater than or equal to the second threshold is less than the third threshold, the RSRP index score is 0; if the sampling proportion where the RSRP measurement result is less than the second threshold is greater than or equal to the third threshold, the RSRP index score is 1; if the sampling proportion where the CQI measurement result is greater than or equal to the fourth threshold is less than the fifth threshold, the CQI index score is 0; if the sampling proportion where the CQI measurement result is greater than or equal to the fourth threshold is greater than or equal to the fifth threshold, the CQI index score is 0; if the sampling proportion where the CQI measurement result is greater than or equal to the fourth threshold is greater than or equal to the fifth threshold, the CQI index score is 1. When the CQI score is equal to the fifth threshold, the CQI score is 1; when the downlink sensing rate measurement result is less than the sixth threshold, the downlink sensing rate score is 0, and when the downlink sensing rate measurement result is greater than or equal to the sixth threshold, the downlink sensing rate score is 1; when the PRB utilization rate measurement result is greater than the seventh threshold, the PRB utilization rate score is 0, and when the PRB utilization rate measurement result is less than or equal to the seventh threshold, the PRB utilization rate score is 1; based on the weights of multiple first sub-measurement indicators, the scores of multiple first sub-measurement indicators are weighted to obtain the candidate churn probability score of the first measurement indicator.

[0120] In one possible design, the determining unit 702 is further configured to: determine the index scores and weights of multiple second sub-measurement indicators; when the number of times the RTT latency measurement result is greater than the eighth threshold is greater than the ninth threshold, the RTT latency index score is 0; when the number of times the RTT latency measurement result is greater than the eighth threshold is less than or equal to the ninth threshold, the RSRP index score is 1; when the HTTP response success rate is less than the tenth threshold, the HTTP response success rate index score is 0; when the HTTP response success rate is greater than or equal to the tenth threshold, the HTTP response success rate index score is 1; and according to the weights of the multiple second sub-measurement indicators, perform weighted processing on the index scores of the multiple second sub-measurement indicators to obtain the candidate churn probability score of the second measurement indicator.

[0121] In one possible design, the determining unit 702 is further configured to: determine the index scores and weights of multiple third sub-measurement indicators; when the measurement result of the number of VoLTE voice call failures is greater than the number threshold, the index score of the number of VoLTE voice call failures is 0, and when the measurement result of the number of VoLTE voice call failures is less than or equal to the number threshold, the index score of the number of VoLTE voice call failures is 1; when the measurement result of the number of VoLTE dropped calls is greater than the number threshold, the index score of the number of VoLTE dropped calls is 0, and when the measurement result of the number of VoLTE dropped calls is less than or equal to the number threshold, the index score of the number of VoLTE dropped calls is 1; and weight the index scores of the multiple third sub-measurement indicators according to their weights to obtain the candidate churn probability score of the third measurement indicator.

[0122] This application also provides a computer-readable storage medium. All or part of the processes in the above method embodiments can be implemented by a computer program instructing related hardware. This program can be stored in the computer-readable storage medium, and when executed, it can include the processes of the above method embodiments. The computer-readable storage medium can be an internal storage unit of the determining device (including a data sending end and / or a data receiving end) in any of the foregoing embodiments, such as a hard disk or memory of the determining device. The computer-readable storage medium can also be an external storage device of the terminal device, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the terminal device. Further, the computer-readable storage medium can include both the internal storage unit of the determining device and an external storage device. The computer-readable storage medium is used to store the computer program and other programs and data required by the determining device. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0123] It should be noted that the terms "first" and "second" in the specification, claims, and drawings of this application are used differently.

[0124] The terms "including" and "having" are used to distinguish different objects, not to describe a specific order.

[0125] And any variations thereof, intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the steps or units listed, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or apparatus.

[0126] It should be understood that in this application, "at least one (item)" means one or more, "more than" means two or more, "at least two (items)" means two or three or more, and "and / or" is used to describe the association relationship of 0 related objects, indicating that there can be three relationships. For example, "A and / or B" can mean: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example,

[0127] At least one of a, b, or c can be used to represent: a, b, c, "a and b", "a and c", "b and c", 5, or "a and b and c", where a, b, and c can be a single or multiple.

[0128] Through the above description of the embodiments, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0129] 0. It should be understood that the disclosed apparatus and methods can be implemented in other ways, given the several embodiments provided in this application. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another apparatus, or some features may be ignored.

[0130] Or not. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device, or unit, and can be electrical, mechanical, or other forms.

[0131] The unit described as a separate component may or may not be physically separate. The component shown as a unit may be one physical unit or multiple physical units, that is, it may be located in one place, or it may be...

[0132] The units can be distributed to multiple different locations. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0133] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0134] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, essentially, or the parts that contribute to the prior art, or all or part of the technical solutions, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0135] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for determining potential churned users, characterized in that, The method includes: Obtain measurement reports for the target cell where the user is located within a historical time period; the measurement reports include measurement results for various types of measurement indicators; For the measurement indicators of the first type, determine the candidate churn probability score and weight corresponding to the measurement results of the measurement indicators of the first type; the first type can be any one of the multiple types; Based on the weight of each type of measurement indicator, the multiple candidate churn probability scores are weighted to obtain the user's churn probability score. If the churn probability score is greater than a first threshold, the user is determined to be a potential churn user. The various types of measurement indicators include a first measurement indicator, a second measurement indicator, and a third measurement indicator; The first measurement index includes multiple first sub-measurement indices, including Received Power (RSRP), Channel Quality Indicator (CQI), Downlink Sensing Rate, and Uplink / Downlink Physical Resource Block (PRB) Utilization. The second measurement metric includes multiple second sub-measurement metrics, including round-trip time (RTT) and HTTP response success rate. The third measurement indicator includes multiple third sub-measurement indicators, including the number of VoLTE voice calls that were not connected and the number of VoLTE dropped calls. Determining the candidate churn probability score for the first measurement indicator includes: Determine the index scores and weights of the plurality of first sub-measurement indicators; Where the sampling ratio of the RSRP measurement result being greater than or equal to the second threshold is less than the third threshold, the RSRP index score is 0; where the sampling ratio of the RSRP measurement result being less than the second threshold is greater than or equal to the third threshold, the RSRP index score is 1. If the sampling ratio of the CQI measurement result being greater than or equal to the fourth threshold is less than the fifth threshold, the CQI index score is 0; if the sampling ratio of the CQI measurement result being greater than or equal to the fourth threshold is greater than or equal to the fifth threshold, the CQI index score is 1. If the measured downlink sensing rate is less than the sixth threshold, the index score of the downlink sensing rate is 0; if the measured downlink sensing rate is greater than or equal to the sixth threshold, the index score of the downlink sensing rate is 1. If the measured result of the PRB utilization rate is greater than the seventh threshold, the index score of the PRB utilization rate is 0; if the measured result of the PRB utilization rate is less than or equal to the seventh threshold, the index score of the PRB utilization rate is 1. Based on the weights of the plurality of first sub-measurement indicators, the indicator scores of the plurality of first sub-measurement indicators are weighted to obtain the candidate churn probability score of the first measurement indicator. Determining the candidate churn probability score for the second measurement indicator includes: Determine the index scores and weights of the plurality of second sub-measurement indicators; If the number of times the measured RTT delay exceeds the eighth threshold is greater than the ninth threshold, the RTT delay index score is 0; if the number of times the measured RTT delay exceeds the eighth threshold is less than or equal to the ninth threshold, the RTT delay index score is 1. If the HTTP response success rate is less than the tenth threshold, the HTTP response success rate metric score is 0; if the HTTP response success rate is greater than or equal to the tenth threshold, the HTTP response success rate metric score is 1. Based on the weights of the plurality of second sub-measurement indicators, the indicator scores of the plurality of second sub-measurement indicators are weighted to obtain the candidate churn probability score of the second measurement indicator. Determining the candidate churn probability score for the third measurement indicator includes: Determine the index scores and weights of the multiple third sub-measurement indicators; If the measured number of missed VoLTE calls is greater than the threshold, the score for the VoLTE missed call count is 0; if the measured number of missed VoLTE calls is less than or equal to the threshold, the score for the VoLTE missed call count is 1. If the measured number of VoLTE dropped calls is greater than the threshold, the score for the VoLTE dropped call count is 0; if the measured number of VoLTE dropped calls is less than or equal to the threshold, the score for the VoLTE dropped call count is 1. Based on the weights of the multiple third sub-measurement indicators, the indicator scores of the multiple third sub-measurement indicators are weighted to obtain the candidate churn probability score of the third measurement indicator.

2. A device for determining potential churned users, characterized in that, The device includes: an acquisition unit, a determination unit, and a processing unit; The acquisition unit is used to acquire the user's measurement report within a historical time period in the target cell; the measurement report includes measurement results of various types of measurement indicators; The determining unit is configured to determine, for the measurement results of the measurement indicators of the first type, the candidate churn probability score and weight corresponding to them; the first type is any one of the multiple types. The processing unit is used to perform weighted processing on multiple candidate churn probability scores according to the weight of each type of measurement index to obtain the user's churn probability score. The determining unit is further configured to determine the user as a potential churn user if the churn probability score is greater than a first threshold. The various types of measurement indicators include a first measurement indicator, a second measurement indicator, and a third measurement indicator; The first measurement index includes multiple first sub-measurement indices, including Received Power (RSRP), Channel Quality Indicator (CQI), Downlink Sensing Rate, and Uplink / Downlink Physical Resource Block (PRB) Utilization. The second measurement metric includes multiple second sub-measurement metrics, including round-trip time (RTT) and HTTP response success rate. The third measurement indicator includes multiple third sub-measurement indicators, including the number of VoLTE voice calls that were not connected and the number of VoLTE dropped calls. The determining unit is specifically used for: Determine the index scores and weights of the plurality of first sub-measurement indicators; Where the sampling ratio of the RSRP measurement result being greater than or equal to the second threshold is less than the third threshold, the RSRP index score is 0; where the sampling ratio of the RSRP measurement result being less than the second threshold is greater than or equal to the third threshold, the RSRP index score is 1. If the sampling ratio of the CQI measurement result being greater than or equal to the fourth threshold is less than the fifth threshold, the CQI index score is 0; if the sampling ratio of the CQI measurement result being greater than or equal to the fourth threshold is greater than or equal to the fifth threshold, the CQI index score is 1. If the measured downlink sensing rate is less than the sixth threshold, the index score of the downlink sensing rate is 0; if the measured downlink sensing rate is greater than or equal to the sixth threshold, the index score of the downlink sensing rate is 1. If the measured result of the PRB utilization rate is greater than the seventh threshold, the index score of the PRB utilization rate is 0; if the measured result of the PRB utilization rate is less than or equal to the seventh threshold, the index score of the PRB utilization rate is 1. Based on the weights of the plurality of first sub-measurement indicators, the indicator scores of the plurality of first sub-measurement indicators are weighted to obtain the candidate churn probability score of the first measurement indicator. The determining unit is further configured to: Determine the index scores and weights of the plurality of second sub-measurement indicators; If the number of times the measured RTT latency exceeds the eighth threshold is greater than the ninth threshold, the downlink sensing rate index score is 0; if the number of times the measured RTT latency exceeds the eighth threshold is less than or equal to the ninth threshold, the RTT latency index score is 1. If the HTTP response success rate is less than the tenth threshold, the HTTP response success rate metric score is 0; if the HTTP response success rate is greater than or equal to the tenth threshold, the HTTP response success rate metric score is 1. Based on the weights of the plurality of second sub-measurement indicators, the indicator scores of the plurality of second sub-measurement indicators are weighted to obtain the candidate churn probability score of the second measurement indicator. The determining unit is further configured to: Determine the index scores and weights of the multiple third sub-measurement indicators; If the measured number of missed VoLTE calls is greater than the threshold, the score for the VoLTE missed call count is 0; if the measured number of missed VoLTE calls is less than or equal to the threshold, the score for the VoLTE missed call count is 1. If the measured number of VoLTE dropped calls is greater than the threshold, the score for the VoLTE dropped call count is 0; if the measured number of VoLTE dropped calls is less than or equal to the threshold, the score for the VoLTE dropped call count is 1. Based on the weights of the multiple third sub-measurement indicators, the indicator scores of the multiple third sub-measurement indicators are weighted to obtain the candidate churn probability score of the third measurement indicator.

3. A computer-readable storage medium, characterized in that, The readable storage medium stores instructions that, when executed, implement the method as described in claim 1.

4. A device for determining potential churned users, characterized in that, include: The processor, memory, and communication interface; wherein the communication interface is used for communication between the device for determining the potential off-network user and other devices or networks; The memory is used to store one or more programs, the one or more programs including computer-executable instructions, which, when the device for determining the potential off-grid user is running, are executed by the processor to execute the computer-executable instructions stored in the memory, so that the device for determining the potential off-grid user performs the method of claim 1.

Images